SOTAVerified

Multi-Armed Bandits

Multi-armed bandits refer to a task where a fixed amount of resources must be allocated between competing resources that maximizes expected gain. Typically these problems involve an exploration/exploitation trade-off.

( Image credit: Microsoft Research )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 181–190 of 1262 papers

TitleStatusHype
Efficient Prompt Optimization Through the Lens of Best Arm Identification—0
Quantile Multi-Armed Bandits: Optimal Best-Arm Identification and a Differentially Private Scheme—0
Best-Arm Identification in Correlated Multi-Armed Bandits—0
Best Arm Identification in Linked Bandits—0
Balanced off-policy evaluation in general action spaces—0
Best Arm Identification in Restless Markov Multi-Armed Bandits—0
Best Arm Identification in Stochastic Bandits: Beyond β-optimality—0
Best Arm Identification under Additive Transfer Bandits—0
An Empirical Evaluation of Thompson Sampling—0
Balanced Linear Contextual Bandits—0
Show:102550
← PrevPage 19 of 127Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1NeuralLinear FullPosterior-MRCumulative regret1.92—Unverified
2Linear FullPosterior-MRCumulative regret1.82—Unverified